An ensemble long short-term memory neural network for hourly PM2. 5 concentration forecasting

Y Bai, B Zeng, C Li, J Zhang - Chemosphere, 2019 - Elsevier
… PM 2.5 concentration forecasting is an essential and effective … for hourly PM 2.5 concentration
forecasting. The presented … as inputs to forecast the next mode information of the PM 2.5 …

PM2. 5 concentrations forecasting in Beijing through deep learning with different inputs, model structures and forecast time

J Yang, R Yan, M Nong, J Liao, F Li, W Sun - Atmospheric Pollution …, 2021 - Elsevier
… In this study, the PM 2.5 concentration forecasting models based on the CNN, LSTM and
CNN-LSTM were established respectively. Since it can effectively extract the spatial …

Dynamic forecasting model of short-term PM2. 5 concentration based on machine learning

L DAI, C ZHANG, L MA - Journal of Computer Applications, 2017 - joca.cn
… well forecast PM2.5 concentration in 24 hours in advance, and effectively forecast the
nighttime average concentration, daytime average concentration and daily average concentration

[PDF][PDF] Evaluation of different machine learning approaches to forecasting PM2. 5 mass concentrations

H Karimian, Q Li, C Wu, Y Qi, Y Mo, G Chen… - Aerosol and Air Quality …, 2019 - aaqr.org
PM2.5 concentrations and predicted 75% of the pollution levels, proving that this methodology
can be effective for forecasting … three methods to forecast PM2.5 concentrations, including …

Effective PM2. 5 concentration forecasting based on multiple spatial–temporal GNN for areas without monitoring stations

IF Su, YC Chung, C Lee, PM Huang - Expert Systems with Applications, 2023 - Elsevier
… Therefore, a GNN-based model was designed in this study to forecast PM2.5 concentrations.
GNN and GRU were used in combination to obtain the spatial and temporal relationships …

A novel multi-factor & multi-scale method for PM2. 5 concentration forecasting

W Yuan, K Wang, X Bo, L Tang, J Wu - Environmental Pollution, 2019 - Elsevier
… This step involves individual prediction at each timescale based on an effective forecasting
model, and ensemble prediction in terms of a linear combination across different timescales. …

PM2. 5 concentration forecasting at surface monitoring sites using GRU neural network based on empirical mode decomposition

G Huang, X Li, B Zhang, J Ren - Science of the Total Environment, 2021 - Elsevier
… was used to validate the effectiveness of the EMD-… effectively predicts the hourly PM2.5
concentration value of the next hour based on the meteorological data and PM2.5 concentration

Modelling and Forecasting Temporal PM2.5 Concentration Using Ensemble Machine Learning Methods

OA Ejohwomu, O Shamsideen Oshodi, M Oladokun… - Buildings, 2022 - mdpi.com
… machine learning methods that have emerged as a result of advancements in data
science, this study examines the effectiveness of using ensemble models for forecasting the …

A novel hybrid strategy for PM2. 5 concentration analysis and prediction

P Jiang, Q Dong, P Li - Journal of environmental management, 2017 - Elsevier
… and effective framework, termed HML-AFNN, was successfully developed to analyse and
forecast the concentration … accurate air pollutant concentration forecasting. For recent air quality …

An improved deep learning model for predicting daily PM2. 5 concentration

F Xiao, M Yang, H Fan, G Fan, MAA Al-Qaness - Scientific reports, 2020 - nature.com
… , and the results demonstrated the effectiveness of our model in predicting daily PM2.5 … as
the study area for constructing the PM2.5 concentration forecasting model. Figure 1 shows the …